Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    patterns involving punctuation and parentheses in structured text or code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    closing parentheses and commas that mark the end of clauses or list items.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    SharedCtor
    -0.80
    Personensuche
    -0.75
     OFDb
    -0.73
    tagHelperRunner
    -0.69
     AssemblyCulture
    -0.69
    RectangleBorder
    -0.68
     متعلقه
    -0.66
     Numerade
    -0.65
    outWeight
    -0.63
    Aholisi
    -0.63
    POSITIVE LOGITS
     Ta
    0.44
    Ta
    0.43
     Cho
    0.38
    ta
    0.29
    cho
    0.29
     Che
    0.29
    Cho
    0.28
     ta
    0.28
     American
    0.27
     franca
    0.27
    Act Density 0.060%

    No Known Activations